{"total":19,"rows":[{"id":"2101.12037","title":"BENDR: using transformers and a contrastive self-supervised learning task to learn from massive amounts of EEG data","created":"2021-01-28","cited_by_count":199,"area":null},{"id":"2212.10426","title":"Deep Riemannian Networks for End-to-End EEG Decoding","created":"2022-12-20","cited_by_count":11,"area":null},{"id":"2402.02754","title":"Focal Modulation Networks for Interpretable Sound Classification","created":"2024-02-05","cited_by_count":8,"area":null},{"id":"2104.09489","title":"Interpreting intermediate convolutional layers of generative CNNs trained on waveforms","created":"2021-04-19","cited_by_count":6,"area":null},{"id":"2210.01719","title":"Learning Temporal Resolution in Spectrogram for Audio Classification","created":"2022-10-04","cited_by_count":4,"area":null},{"id":"2101.11306","title":"Learning Non-linear Wavelet Transformation via Normalizing Flow","created":"2021-01-27","cited_by_count":3,"area":null},{"id":"2107.10790","title":"Interpretable SincNet-based Deep Learning for Emotion Recognition from EEG brain activity","created":"2021-07-18","cited_by_count":3,"area":null},{"id":"2110.02375","title":"Interpreting intermediate convolutional layers in unsupervised acoustic word classification","created":"2021-10-05","cited_by_count":3,"area":null},{"id":"2209.01992","title":"TFN: An Interpretable Neural Network with Time-Frequency Transform Embedded for Intelligent Fault Diagnosis","created":"2022-09-05","cited_by_count":3,"area":null},{"id":"2311.07037","title":"Phonological Level wav2vec2-based Mispronunciation Detection and Diagnosis Method","created":"2023-11-13","cited_by_count":3,"area":null},{"id":"2111.02654","title":"Speech recognition for air traffic control via feature learning and end-to-end training","created":"2021-11-04","cited_by_count":2,"area":null},{"id":"2407.06606","title":"Tailored Design of Audio-Visual Speech Recognition Models using Branchformers","created":"2024-07-09","cited_by_count":2,"area":null},{"id":"2506.02181","title":"Echoes of Phonetics: Unveiling Relevant Acoustic Cues for ASR via Feature Attribution","created":"2025-06-02","cited_by_count":2,"area":null},{"id":"2405.01815","title":"Toward end-to-end interpretable convolutional neural networks for waveform signals","created":"2024-05-03","cited_by_count":1,"area":null},{"id":"2206.13365","title":"Interpretable Acoustic Representation Learning on Breathing and Speech Signals for COVID-19 Detection","created":"2022-06-27","cited_by_count":0,"area":null},{"id":"2209.10223","title":"Dynamic Time-Alignment of Dimensional Annotations of Emotion using Recurrent Neural Networks","created":"2022-09-21","cited_by_count":0,"area":null},{"id":"2502.17463","title":"SincPD: An Explainable Method based on Sinc Filters to Diagnose Parkinson's Disease Severity by Gait Cycle Analysis","created":"2025-02-10","cited_by_count":0,"area":null},{"id":"2505.23964","title":"Acoustic Classification of Maritime Vessels using Learnable Filterbanks","created":"2025-05-29","cited_by_count":0,"area":null},{"id":"2607.08545","title":"Structural Bottlenecks on Frequency Representation in End-to-End Audio Models","created":"2026-07-09","cited_by_count":0,"area":null}],"next_cursor":null}